NLP systems rarely give special consideration to numbers found in text. This starkly contrasts with the consensus in neuroscience that, in the brain, numbers are represented differently from words. We arrange recent NLP work on numeracy into a comprehensive taxonomy of tasks and methods. We break down the subjective notion of numeracy into 7 subtasks, arranged along two dimensions: granularity (exact vs approximate) and units (abstract vs grounded). We analyze the myriad representational choices made by over a dozen previously published number encoders and decoders. We synthesize best practices for representing numbers in text and articulate a vision for holistic numeracy in NLP, comprised of design trade-offs and a unified evaluation.

No abstract

NLP systems rarely give special consideration to numbers found in text. This starkly contrasts with the consensus in neuroscience that, in the brain, numbers are represented differently from words. We arrange recent NLP work on numeracy into a comprehensive taxonomy of tasks and methods. We break down the subjective notion of numeracy into 7 subtasks, arranged along two dimensions: granularity (exact vs approximate) and units (abstract vs grounded). We analyze the myriad representational choices made by 18 previously published number encoders and decoders. We synthesize best practices for representing numbers in text and articulate a vision for holistic numeracy in NLP, comprised of design trade-offs and a unified evaluation.

Downstream evaluation of pretrained word embeddings is expensive, more so for tasks where current state of the art models are very large architectures. Intrinsic evaluation using word similarity or analogy datasets, on the other hand, suffers from several disadvantages. We propose a novel intrinsic evaluation task employing large word association datasets (particularly the Small World of Words dataset). We observe correlations not just between performances on SWOW-8500 and previously proposed intrinsic tasks of word similarity prediction, but also with downstream tasks (eg. Text Classification and Natural Language Inference). Most importantly, we report better confidence intervals for scores on our word association task, with no fall in correlation with downstream performance.

No abstract